doorman ollama queuing proxy
For source, see ~arrdem/source/projects/doorman.
Loaded Models
none
Queue
0
In-Flight
0
Slots Available
2
Queue
| State |
User |
Model |
Endpoint |
Wait |
| No active requests |
Users
| User |
Requests |
Input Tokens |
Output Tokens |
Time |
Cost |
| localscene |
44 |
172,877 |
147,466 |
36.6m |
$0.2850 |
| craisis |
1 |
0 |
0 |
0s |
$0.0000 |
Models
| Model |
Status |
Input Tokens |
Output Tokens |
Context (tok/s) |
Generate (tok/s) |
| gemma4:e2b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| gemma4:e4b |
unloaded |
172,877 |
147,466 |
29797.8 |
194.5 |
| gemma4:26b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3.5:122b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3.5:35b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| gemma4:31b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| deepseek-r1:32b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| devstral-small-2:latest |
unloaded |
0 |
0 |
0.0 |
0.0 |
| devstral:24b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| devstral-2:123b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3-coder-next:latest |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:30b-thinking |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:4b-instruct |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:1.7b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:0.6b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:4b-thinking |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:30b-instruct |
unloaded |
0 |
0 |
0.0 |
0.0 |
| deepseek-coder:33b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3-coder:30b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:30b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3-next:80b |
unloaded |
0 |
0 |
0.0 |
0.0 |
| qwen3:30b-a3b-q8_0 |
unloaded |
0 |
0 |
0.0 |
0.0 |